Computer Vision News - June 2019

28 Challenge and Workshop - CVPR 2019 Computer Vision News Among the organizers of the Long-Term Visual Localization under Changing Conditions workshop at CVPR 2019, Vassileios Balntas and Torsten Sattler share their insights on the challenges of long-term visual localization and the ways in which accurate long-term visual localization provides a vital component in many computer vision and robotics scenarios, including autonomous vehicles such as self-driving cars and other robots, augmented reality, structure-from-motion, and simultaneous localization and mapping (SLAM). Challenge With CVPR 2019 right around the corner, researchers in the field of computer vision and pattern recognition look ahead to the upcoming programs and presentations. The Long-Term Visual Localization under Changing Conditions workshop stands out as one of the most highly- anticipated events of the conference. Experts in the field from across industry and academia will attend the workshop to discuss practical challenges of developing visual localization under changing conditions. Vassileios Balntas and Torsten Sattler, along with the other organizers, have been working on visual localization for quite some time. Vassileios Balntas leads the research team at Scape Technologies , which focuses on researching fundamental computer vision problems. Meanwhile, Torsten Sattler serves as an associate professor in the Electrical Engineering department at the Chalmers University of Technology . Visual localization refers to the problem of accurately estimating position and orientation from which an image was taken with respect to a scene representation. Torsten shares: “ It’s an interesting problem that we are What Makes a Place a Place